CN116824314A - Information acquisition method and system - Google Patents
Information acquisition method and system Download PDFInfo
- Publication number
- CN116824314A CN116824314A CN202210272796.0A CN202210272796A CN116824314A CN 116824314 A CN116824314 A CN 116824314A CN 202210272796 A CN202210272796 A CN 202210272796A CN 116824314 A CN116824314 A CN 116824314A
- Authority
- CN
- China
- Prior art keywords
- information
- user
- recognition model
- verification
- face
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000012795 verification Methods 0.000 claims abstract description 161
- 238000012549 training Methods 0.000 claims abstract description 133
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 49
- 238000005457 optimization Methods 0.000 claims abstract description 16
- 238000004590 computer program Methods 0.000 claims description 14
- 238000004422 calculation algorithm Methods 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000010365 information processing Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 12
- 230000007613 environmental effect Effects 0.000 description 18
- 238000010586 diagram Methods 0.000 description 7
- 230000001815 facial effect Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000002372 labelling Methods 0.000 description 3
- 238000011176 pooling Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 210000000056 organ Anatomy 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 210000005069 ears Anatomy 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000036548 skin texture Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Collating Specific Patterns (AREA)
- Image Analysis (AREA)
Abstract
The invention provides an information acquisition method and system, which can be applied to the field of payment security, wherein the method comprises the following steps: pre-training the convolutional neural network by using a first training sample to obtain an image recognition model; performing optimization training on the image recognition model by using a second training sample to obtain a target image recognition model; carrying out face verification on the received identity verification information uploaded by the user terminal, and carrying out position verification on the identity verification information based on a target image recognition model; and under the condition that the face verification and the position verification are both passed, transmitting the received data information corresponding to the information acquisition request transmitted by the user terminal to the user terminal. The system is used for executing the method. The invention can realize double security guarantee of user identity and user environment through double identity authentication of face authentication and position authentication, and avoid property loss of users caused by authentication of user identity based on image processing means of some illegal user terminals.
Description
Technical Field
The present invention relates to the field of information processing technologies, and in particular, to an information acquisition method and system.
Background
In the prior art, the face recognition mode mainly comprises the steps of singly acquiring the facial features of a user, and then matching the facial features with features in a feature library to realize identity recognition, wherein the mode can only judge the identity of the user and cannot recognize the safety of user environment information, and the user identity verification is performed on the basis of an image processing means for an illegal user terminal, so that the property loss of the user is caused. It can be seen that how to eliminate the security problem existing in the consumption or payment environment has become a technical problem to be solved.
Disclosure of Invention
The information acquisition method and the system provided by the invention are used for solving the problems in the prior art, and can realize double security guarantee of user identity and user environment through double identity authentication of face authentication and position authentication, thereby avoiding property loss of users caused by authentication of user identity based on image processing means of some illegal user terminals.
The invention provides an information acquisition method, which comprises the following steps:
pre-training the convolutional neural network by using a first training sample to obtain an image recognition model;
performing optimization training on the image recognition model by using a second training sample to obtain a target image recognition model;
Carrying out face verification on the received identity verification information uploaded by the user terminal, and carrying out position verification on the identity verification information based on the target image recognition model;
under the condition that the face verification and the position verification are both passed, the received data information corresponding to the information acquisition request sent by the user terminal is sent to the user terminal;
the first training sample is obtained by marking each environment image according to first position information corresponding to each environment image in a plurality of acquired environment images;
the second training sample is determined according to a target image obtained by overlapping the face image and the environment image in the first training sample;
the identity verification information comprises an environment image including a face image of the user and position information of the user, wherein the environment image is shot by the user in real time.
According to the information acquisition method provided by the invention, the convolutional neural network is pre-trained by using the first training sample to acquire the image recognition model, and the method comprises the following steps:
inputting the first training sample into the convolutional neural network for pre-training, and adjusting the super-parameters of the convolutional neural network according to the comparison result of the second position information and the first position information of each environment image output by the convolutional neural network;
And determining the image recognition model according to the adjusted convolutional neural network.
According to the information acquisition method provided by the invention, the optimization training is performed on the image recognition model by using the second training sample so as to acquire a target image recognition model, and the information acquisition method comprises the following steps:
and inputting the second training sample into the image recognition model for optimization training, and optimizing the image recognition model by adopting a back propagation algorithm and a random gradient algorithm according to a comparison result of the third position information of the target image and the first position information output by the image recognition model so as to acquire the target image recognition model.
According to the information acquisition method provided by the invention, the identity verification information processing position uploaded by the user terminal is determined by the following modes:
after receiving the information acquisition request sent by the user terminal, sending authentication information acquisition information to the user terminal, so that the user terminal acquires the authentication information according to the received authentication information acquisition information.
According to the information acquisition method provided by the invention, the face verification is performed on the received identity verification information uploaded by the user terminal, and the position verification is performed on the identity verification information based on the target image recognition model, and the method comprises the following steps:
Extracting first face features of the environment image comprising the face image of the user;
performing feature vector calculation on the first face feature and a second face feature when a user registers in the identity verification information to obtain a distance between the first face feature and the second face feature;
according to the distance, finishing face verification of the identity verification information;
and under the condition that the face verification is passed, carrying out position verification on the identity verification information based on the target image recognition model.
According to the information acquisition method provided by the invention, the position verification of the identity verification information based on the target image recognition model comprises the following steps:
and inputting the environment image comprising the face image of the user into the target image recognition model, and completing the position verification of the identity verification information according to the comparison result of the fourth position information output by the target image recognition model and the position information of the user.
The invention also provides an information acquisition system, which comprises: the system comprises a first training module, a second training module, an identity verification module and an information acquisition module;
the first training module is used for pre-training the convolutional neural network by using a first training sample so as to obtain an image recognition model;
The second training module is used for carrying out optimization training on the image recognition model by using a second training sample so as to obtain a target image recognition model;
the identity verification module is used for carrying out face verification on the received identity verification information uploaded by the user terminal and carrying out position verification on the identity verification information based on the target image recognition model;
the information acquisition module is used for transmitting the received data information corresponding to the information acquisition request transmitted by the user terminal to the user terminal under the condition that the face verification and the position verification are both passed;
the first training sample is obtained by marking each environment image according to first position information corresponding to each environment image in a plurality of acquired environment images;
the second training sample is determined according to a target image obtained by overlapping the face image and the environment image in the first training sample;
the identity verification information comprises an environment image including a face image of the user and position information of the user, wherein the environment image is shot by the user in real time.
The invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the information acquisition method as described above when executing the program.
The present invention also provides a processor-readable storage medium storing a computer program for causing the processor to execute the information acquisition method as described in any one of the above.
The invention also provides a computer program product comprising a computer program which, when executed by a processor, implements a method of information acquisition as described in any of the above.
The information acquisition method and the system can realize double security guarantee of the user identity and the user environment through double identity authentication of face authentication and position authentication, avoid some illegal user terminals, and cause property loss of the user through authentication of the user identity based on an image processing means.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of an information acquisition method provided by the invention;
FIG. 2 is a schematic diagram of a convolutional neural network provided by the present invention;
FIG. 3 is a schematic diagram of a convolutional neural network according to the second embodiment of the present invention;
fig. 4 is a schematic structural diagram of an acceptance module in the convolutional neural network provided by the invention;
FIG. 5 is a schematic diagram of the information acquisition system according to the present invention;
fig. 6 is a schematic diagram of the physical structure of the electronic device provided by the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
When a user enters an Internet application for the first time, personal information is required to be filled in and a mobile phone number is bound (a short message verification code is sent) to register an Internet application account, in the normal use process of the user, if sensitive operations such as payment, password recovery and the like are involved, the existing Internet application usually adopts a short message verification code checking mode and face recognition mode to identify the identity of the user, so that the user identity verification mode is determined to be the principal operation, the user payment environment safety cannot be ensured usually, and the invention provides an information acquisition method.
Fig. 1 is a flow chart of an information acquisition method provided by the present invention, as shown in fig. 1, the method includes:
step 100, pre-training a convolutional neural network by using a first training sample to obtain an image recognition model;
step 200, performing optimization training on the image recognition model by using a second training sample to obtain a target image recognition model;
step 300, carrying out face verification on the received identity verification information uploaded by the user terminal, and carrying out position verification on the identity verification information based on a target image recognition model;
step 400, under the condition that the face verification and the position verification are both passed, transmitting the received data information corresponding to the information acquisition request transmitted by the user terminal to the user terminal;
the first training sample is obtained by marking each environment image according to first position information corresponding to each environment image in a plurality of acquired environment images;
the second training sample is determined according to the target image obtained by overlapping the face image and the environment image in the first training sample;
the authentication information comprises an environment image including a face image of the user and position information of the user, which are shot by the user in real time.
It should be noted that, the execution subject of the above method may be a computer device.
Optionally, the method comprises the steps of labeling the position information corresponding to each environmental image in a plurality of acquired environmental images in a position label mode to obtain a first training sample, and inputting the first training sample into a convolutional neural network for training and learning to obtain an image recognition model.
The environmental image refers to a picture including objects in a natural scene, and may specifically include a building picture, a street view picture, a building indoor picture, and the like. When the environmental image is acquired, acquiring the acquisition position information (i.e. the first position information) corresponding to the environmental image at the same time, and labeling the environmental image by the first position information to obtain a first training sample, for example, labeling content may be city street.
Mining the relation between the environment image and the position information based on the image recognition model; and then, carrying out random superposition combination on the face image and the environment image in the first training sample, inputting the face image and the environment image into an image recognition model to obtain position information corresponding to the face image and the environment image, comparing the position information with a position label corresponding to the environment image, and optimizing the image recognition model to obtain the target image recognition model.
The random superposition of the environmental images of the face images in the second training sample means that after the face images and the environmental images are freely combined, the environmental images are used as background images, and the face images are used as foreground images to perform layer superposition.
And when the identity authentication is performed, performing face recognition on the received identity authentication information uploaded by the user terminal (comprising the environment image including the face image of the user and the position information of the user shot by the user in real time), finishing the face authentication on the identity authentication information uploaded by the user terminal according to the face recognition result, and performing the position authentication on the identity authentication information based on the target image recognition model obtained through training.
When user identity verification is carried out, acquiring user identity verification information comprising an environment image of a user face image and user position information, inputting the environment image comprising the user face image into a target image recognition model to obtain predicted position information, then matching the predicted position information with the acquired position information of the user to complete the position verification of the user, and finally realizing the position verification and the face verification of the user by combining a face verification result.
For example, the face verification of the user may be completed by matching the face features of the environmental image including the face image of the user with the face features of the user pre-stored in the feature library.
And under the condition that the face verification and the position verification are both passed, transmitting the received data information corresponding to the information acquisition request transmitted by the user terminal to the user terminal.
The information acquisition method provided by the invention can realize double security guarantee of the user identity and the user environment through double identity authentication of face authentication and position authentication, avoids some illegal user terminals, and causes property loss of the user through authentication of the user identity based on an image processing means.
Further, in one embodiment, step 100 may specifically include:
step 1001, inputting a first training sample into a convolutional neural network for pre-training, and adjusting the hyper-parameters of the convolutional neural network according to the comparison result of the second position information and the first position information of each environmental image output by the convolutional neural network;
step 1002, determining an image recognition model according to the adjusted convolutional neural network.
Optionally, in step 1001, the obtained first training sample may be input into a convolutional neural network as shown in fig. 2 for pre-training, where the convolutional neural network has a multi-layer network structure and is also a multi-layer non-fully connected neural network.
Functionally, the convolution layer and the pooling layer are mainly used for extracting the features of the image to finish the mapping of the features of the image from low dimension to high dimension, and the full-connection layer is used for finishing the conversion of the features of the high dimension to the image category.
Optionally, the invention uses a deep convolutional network Recog-Net based on GoogleNet as a convolutional neural network, and the structure of the convolutional neural network is shown in the following figures 3 and 4:
fig. 3 is an overall structure of the convolutional neural network, and fig. 4 is a structure diagram of the admission module in fig. 3. In fig. 3, the input to the convolutional neural network is an RGB three-channel ambient image of size 229 x 3, followed by three stages of convolutional operations C1, C2, C3, followed by a concomitant p1 pooling dimension reduction and convolution of C4, C5 to extract more abstract high-level features.
As shown in fig. 4, the core of the convolutional neural network is an acceptance module, and the whole acceptance module is composed of convolution kernels with three different scales, namely 1×1,3×3 and 5*5. Meanwhile, the convolutional neural network is stacked together in cooperation with pooling operation (3*3) (the sizes of the convolutions and the pooled products are the same, and the channels are added), so that the width of the convolutional neural network is increased, and the fit of the convolutional neural network to the dimension is also increased. After each convolution layer, a ReLU operation is performed, and the ReLU function can be used as a nonlinear activation function to effectively fit the training state of the convolution neural network.
In the pre-training stage, the prediction result of the convolutional neural network is compared with the first position information marked by the corresponding first training sample, and then the convolutional neural network is optimized according to the comparison result, specifically, the super-parameters of the convolutional neural network can be optimized and adjusted, so that the adjusted super-parameters are determined, and an image recognition model is obtained according to the adjusted convolutional neural network.
According to the information acquisition method provided by the invention, the convolutional neural network is trained by using the first training sample so as to acquire the image recognition model, so that a foundation is laid for acquiring the target recognition model based on the image recognition network subsequently and finally realizing user position verification.
Further, in one embodiment, step 200 may specifically include:
step 2001, inputting a second training sample into the image recognition model for optimization training, and optimizing the image recognition model by adopting a back propagation algorithm and a random gradient algorithm according to a comparison result of the third position information and the first position information of the target image output by the image recognition model so as to obtain the target image recognition model.
Optionally, the second training sample is input into the image recognition model obtained by pre-training in step 100, the position data (i.e. the third position information) obtained by predicting the image recognition model is compared with the position information (consistent with the first position information) of the environmental image marked in the second training sample, the image recognition model is optimized by adopting a continuous back propagation algorithm and combining a random gradient descent algorithm with a dynamic change learning rate according to the comparison result, the optimized image recognition model is obtained, and the optimized image recognition model is used as the target image recognition model.
For example, the position recognition of the environment image in the invention can be the position recognition of the building image, in order to enable the target image recognition model obtained by training to have more accurate discrimination capability, the invention uses the original building image as a first training sample to perform convolutional neural network pre-training, so that the image recognition model obtained by training can accurately judge the position of the building; then, carrying out random superposition processing on the face image and the building image, taking the obtained random superposed image as a second training sample to carry out secondary optimization training on the pre-trained image recognition model, so that the target image recognition model obtained after the two times of training can realize accurate prediction of the position of the building image comprising the face image based on the pre-trained image recognition model memory.
According to the information acquisition method provided by the invention, the second training sample is used for training the training image recognition model, so that a foundation is laid for determining the target recognition model based on the trained image recognition network and finally realizing the verification of the user position.
Further, in one embodiment, the location of the authentication information uploaded by the user terminal in step 300 is determined by:
After receiving an information acquisition request sent by a user terminal, sending authentication information acquisition information to the user terminal so that the user terminal acquires the authentication information according to the authentication information acquisition information.
Optionally, in many internet applications, such as WeChat, payment device, mei Tuo, drop, etc., especially like mobile 5G message functions, implementing 5G message related application functions may involve user authentication. The current identity verification is mainly realized through face recognition, fingerprint recognition and the like.
The invention provides a new identity verification mode, which is combined with the position identity verification of the environment image. When using the internet application, the user can acquire the target page information, such as a personal center page, a password payment page and the like, from the server side in a mode of sending an information acquisition request. The information acquisition request includes address data of the target request information, and identity information of the user (such as user terminal identification, user account number or number, etc.).
And the server side sends the identity verification information acquisition information to the user terminal based on the user identity information included in the information acquisition request.
After receiving the identity verification information acquisition information, the user terminal shoots an environment image comprising a user face image and position information of the user through an acquisition device, and uploads the environment image and the position information of the user as the identity verification information to a server, and the server receives the identity verification information to acquire the environment image; meanwhile, the identity verification information comprises user identity information, such as a user mobile phone number.
The acquisition device can specifically acquire an environment image comprising a face image of a user and position information of the user by a built-in camera. The method can also specifically collect the environment image comprising the face image of the user and the position information of the user through an external camera which is associated with the user terminal. For example, the user terminal may be connected to the image capturing device through a connection line or a network, and the image capturing device captures an environmental image including a face image of the user and location information of the user through the camera, and transmits the captured environmental image including the face image of the user and the location information of the user to the user terminal. The cameras may be monocular cameras, binocular cameras, depth cameras, 3D (three-dimensional) cameras, etc. The user terminal can collect images of living bodies in a real scene, and can collect existing images containing faces in the real scene, such as identity document scanning pieces and the like.
The user terminal may be, but not limited to, various smartphones, tablet computers, notebook computers, desktop computers, portable wearable devices, smart speakers, etc. The server may be a server, which may be an independent physical server, or a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, storage, network services, cloud communication, middleware services, domain name services, security services, CDNs, basic cloud computing services such as big data and artificial intelligence platforms, and the like.
According to the information acquisition method, through the environment image including the face image of the user and the position information of the user, which are shot by the user in real time and are included in the authentication information uploaded by the user terminal, double authentication of face authentication and position authentication of the user is realized, and the authentication safety is improved.
Further, in one embodiment, step 400 may specifically include:
step 4001, extracting a first face feature of an environmental image including a face image of a user;
step 4002, performing feature vector calculation on the first face feature and a second face feature when a user registers in the authentication information to obtain a distance between the first face feature and the second face feature;
step 4003, finishing the face verification of the identity verification information according to the distance;
step 4004, in the case that the face verification passes, performing location verification on the authentication information based on the target image recognition model.
Optionally, according to the environment image including the face image of the user in the authentication information uploaded by the user terminal, the service end extracts the face feature, namely the first face feature, from the environment image through the image processing module.
And acquiring the face features obtained during user registration, namely second face features, from a face feature library through the user identity information in the identity verification information.
Facial features are physiological features inherent to a face, such as iris morphology, positional relationship between facial organs (eyes, nose, mouth, ears, etc.), structure of facial organs (shape, size, etc.), skin texture, and the like.
And carrying out feature vector calculation on the first face feature extracted from the environment image including the face image of the user in the authentication information uploaded by the user terminal and the second face feature obtained by the face feature library, for example, obtaining the distance between the first face feature and the second face feature through the mahalanobis distance, completing the face authentication of the environment image including the face image of the user in the authentication information, and if the calculated distance is zero, passing the face authentication.
And under the condition that the face verification is passed, carrying out position verification on the position information of the user in the identity verification information based on the target image recognition model.
According to the information acquisition method provided by the invention, the position information corresponding to the environment image is predicted, the predicted position information is compared with the position information acquired by the user, the environment image verification based on the position information is realized, and the verification safety is improved.
Further, in one embodiment, step 4004 may specifically include:
step 40041, inputting the environment image including the face image of the user into the target image recognition model, and completing the position verification of the identity verification information according to the comparison result of the fourth position information output by the target image recognition model and the position information of the user.
Optionally, the environmental image including the face image of the user is input to the target image recognition model, and the position information (i.e., the fourth position information) of the environmental image including the face feature output by the target image recognition model is compared to complete the position verification of the position information of the user.
For example, the location comparison may be embodied as the location information G of the user to be collected j And fourth position information G obtained by prediction i Comparing, if the collected position information G of the user j Located in predicted fourth position information G i Is of the geographical region of (a)Within the range, the location verification is possible. In the process of position verification, besides simple geographical region range planning, other technologies are utilized to ensure the authenticity of the acquired position information of the user in the process of acquiring the position information of the user.
For example, the real-time position of the user such as map software, weChat and the like is checked to be distinguished from the position information of the user in the authentication information uploaded by the user terminal, so that the authenticity of the acquired position information of the user is ensured.
For another example, a blockchain technology may be introduced, where the server is used as a blockchain node in the blockchain network, and by storing an environmental image including a face image of a user and position information of the user, which are captured by the user in real time, on the blockchain, and acquiring the position information of the user from a data block of the blockchain, the position information of the user uploaded by the user terminal is ensured to be consistent with the position information of the user stored in the blockchain. Blockchains are novel application modes of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanisms, encryption algorithms, and the like. The Blockchain (Blockchain), which is essentially a decentralised database, is a string of data blocks that are generated by cryptographic means in association, each data block containing a batch of information of network transactions for verifying the validity of the information (anti-counterfeiting) and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, and an application services layer.
Where q=1 indicates passing the position verification, and q= -1 indicates not passing the position verification.
When the face verification passes and the position verification passes, data information corresponding to the information acquisition request is sent, and specifically:
when the face verification is passed and the position verification is not passed, the identity verification is not passed;
when the face verification fails, the position verification is not performed, so that the processing time of the verification can be saved;
and when the face verification passes and the position verification passes, transmitting data information corresponding to the information acquisition request transmitted by the received user terminal through the identity verification.
When the user identity authentication is actually performed, the position information of the user in the identity authentication information uploaded by the user terminal can be subjected to position authentication, and when the position authentication fails, the face authentication is not performed, so that the processing time of the authentication is saved.
The information acquisition method provided by the invention can realize double security guarantee of the user identity and the user environment through double identity authentication of face authentication and position authentication, can ensure that the user performs operations such as payment and the like in the safe environment, and avoids some illegal user terminals, and the user property loss is caused by the authentication of the user identity based on an image processing means.
The information acquisition system provided by the present invention will be described below, and the information acquisition system described below and the information acquisition method described above may be referred to correspondingly to each other.
Fig. 5 is a schematic structural diagram of an information acquisition system provided by the present invention, as shown in fig. 5, including:
a first training module 510, a second training module 511, an authentication module 512, and an information acquisition module 513;
a first training module 510, configured to pretrain the convolutional neural network using the first training sample to obtain an image recognition model;
a second training module 511, configured to perform optimization training on the image recognition model using a second training sample to obtain a target image recognition model;
the identity verification module 512 is configured to perform face verification on the received identity verification information uploaded by the user terminal and perform location verification on the identity verification information based on the target image recognition model;
the information obtaining module 513 is configured to send data information corresponding to the received information obtaining request sent by the user terminal to the user terminal when both face verification and location verification pass;
the first training sample is obtained by marking each environment image according to first position information corresponding to each environment image in a plurality of acquired environment images;
The second training sample is determined according to the target image obtained by overlapping the face image and the environment image in the first training sample;
the authentication information comprises an environment image including a face image of the user and position information of the user, which are shot by the user in real time.
The information acquisition system provided by the invention can realize double security guarantee of the user identity and the user environment through double identity authentication of face authentication and position authentication, avoids some illegal user terminals, and causes property loss of the user through authentication of the user identity based on an image processing means.
Further, in one embodiment, the first training module 510 may be further specifically configured to:
inputting the first training sample into a convolutional neural network for pre-training, and adjusting the hyper-parameters of the convolutional neural network according to the comparison result of the second position information and the first position information of each environment image output by the convolutional neural network;
and determining an image recognition model according to the adjusted convolutional neural network.
According to the information acquisition system provided by the invention, the convolutional neural network is trained by using the first training sample so as to acquire the image recognition model, so that a foundation is laid for acquiring the target recognition model based on the image recognition network and finally realizing user position verification.
Further, in one embodiment, the second training module 511 may be further specifically configured to:
and inputting the second training sample into the image recognition model for optimization training, and optimizing the image recognition model by adopting a back propagation algorithm and a random gradient algorithm according to a comparison result of the third position information and the first position information of the target image output by the image recognition model so as to obtain the target image recognition model.
According to the information acquisition system provided by the invention, the second training sample is used for training the training image recognition model, so that a foundation is laid for determining the target recognition model based on the trained image recognition network and finally realizing the verification of the user position.
Further, in one embodiment, the identity verification module 512 may be further specifically configured to:
after receiving an information acquisition request sent by a user terminal, sending authentication information acquisition information to the user terminal so that the user terminal acquires the authentication information according to the authentication information acquisition information.
According to the information acquisition system provided by the invention, through the environment image comprising the user face image and the position information of the user, which are shot by the user in real time and are included in the authentication information uploaded by the user terminal, the dual authentication of the face authentication and the position authentication of the user is realized, and the authentication safety is improved.
Further, in one embodiment, the identity verification module 512 may be further specifically configured to:
extracting first face features of an environment image comprising a user face image;
performing feature vector calculation on the first face feature and the second face feature when the user registers in the identity verification information to obtain the distance between the first face feature and the second face feature;
according to the distance, finishing the face verification of the identity verification information;
and under the condition that the face verification is passed, carrying out position verification on the identity verification information based on the target image recognition model.
According to the information acquisition system provided by the invention, the position information corresponding to the environment image is predicted, the predicted position information is compared with the position information acquired by the user, the environment image verification based on the position information is realized, and the verification safety is improved.
Further, in one embodiment, the identity verification module 512 may be further specifically configured to:
and inputting the environment image comprising the face image of the user into the target image recognition model, and completing the position verification of the identity verification information according to the comparison result of the fourth position information output by the target image recognition model and the position information of the user.
The information acquisition system provided by the invention can realize double security guarantee of the user identity and the user environment through double identity authentication of face authentication and position authentication, can ensure that the user performs operations such as payment and the like in the safe environment, and avoids some illegal user terminals, and the user property loss is caused by the authentication of the user identity based on an image processing means.
Fig. 6 is a schematic physical structure of an electronic device according to the present invention, as shown in fig. 6, the electronic device may include: a processor (processor) 610, a communication interface (communication interface) 611, a memory (memory) 612 and a bus (bus) 613, wherein the processor 610, the communication interface 611, and the memory 612 communicate with each other via the bus 613. The processor 610 may call logic instructions in the memory 612 to perform the following method:
pre-training the convolutional neural network by using a first training sample to obtain an image recognition model;
performing optimization training on the image recognition model by using a second training sample to obtain a target image recognition model;
carrying out face verification on the received identity verification information uploaded by the user terminal, and carrying out position verification on the identity verification information based on a target image recognition model;
Under the condition that the face verification and the position verification pass, the received data information corresponding to the information acquisition request sent by the user terminal is sent to the user terminal;
the first training sample is obtained by marking each environment image according to first position information corresponding to each environment image in a plurality of acquired environment images;
the second training sample is determined according to the target image obtained by overlapping the face image and the environment image in the first training sample;
the authentication information comprises an environment image including a face image of the user and position information of the user, which are shot by the user in real time.
Further, the logic instructions in the memory described above may be implemented in the form of software functional units and stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer power supply screen (which may be a personal computer, a server, or a network power supply screen, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Further, the present invention discloses a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, are capable of performing the information acquisition method provided by the above-mentioned method embodiments, for example comprising:
pre-training the convolutional neural network by using a first training sample to obtain an image recognition model;
performing optimization training on the image recognition model by using a second training sample to obtain a target image recognition model;
carrying out face verification on the received identity verification information uploaded by the user terminal, and carrying out position verification on the identity verification information based on a target image recognition model;
under the condition that the face verification and the position verification pass, the received data information corresponding to the information acquisition request sent by the user terminal is sent to the user terminal;
the first training sample is obtained by marking each environment image according to first position information corresponding to each environment image in a plurality of acquired environment images;
the second training sample is determined according to the target image obtained by overlapping the face image and the environment image in the first training sample;
The authentication information comprises an environment image including a face image of the user and position information of the user, which are shot by the user in real time.
In another aspect, the present invention also provides a processor-readable storage medium storing a computer program for causing the processor to execute the method provided in the above embodiments, for example, including
Pre-training the convolutional neural network by using a first training sample to obtain an image recognition model;
performing optimization training on the image recognition model by using a second training sample to obtain a target image recognition model;
carrying out face verification on the received identity verification information uploaded by the user terminal, and carrying out position verification on the identity verification information based on a target image recognition model;
under the condition that the face verification and the position verification pass, the received data information corresponding to the information acquisition request sent by the user terminal is sent to the user terminal;
the first training sample is obtained by marking each environment image according to first position information corresponding to each environment image in a plurality of acquired environment images;
the second training sample is determined according to the target image obtained by overlapping the face image and the environment image in the first training sample;
The authentication information comprises an environment image including a face image of the user and position information of the user, which are shot by the user in real time.
The system embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer power screen (which may be a personal computer, a server, or a network power screen, etc.) to perform the method described in the various embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. An information acquisition method, characterized by comprising:
pre-training the convolutional neural network by using a first training sample to obtain an image recognition model;
performing optimization training on the image recognition model by using a second training sample to obtain a target image recognition model;
carrying out face verification on the received identity verification information uploaded by the user terminal, and carrying out position verification on the identity verification information based on the target image recognition model;
under the condition that the face verification and the position verification are both passed, the received data information corresponding to the information acquisition request sent by the user terminal is sent to the user terminal;
The first training sample is obtained by marking each environment image according to first position information corresponding to each environment image in a plurality of acquired environment images;
the second training sample is determined according to a target image obtained by overlapping the face image and the environment image in the first training sample;
the identity verification information comprises an environment image including a face image of the user and position information of the user, wherein the environment image is shot by the user in real time.
2. The method of claim 1, wherein the pre-training the convolutional neural network using the first training sample to obtain the image recognition model comprises:
inputting the first training sample into the convolutional neural network for pre-training, and adjusting the super-parameters of the convolutional neural network according to the comparison result of the second position information and the first position information of each environment image output by the convolutional neural network;
and determining the image recognition model according to the adjusted convolutional neural network.
3. The information acquisition method according to claim 1, wherein the optimally training the image recognition model using the second training sample to acquire a target image recognition model includes:
And inputting the second training sample into the image recognition model for optimization training, and optimizing the image recognition model by adopting a back propagation algorithm and a random gradient algorithm according to a comparison result of the third position information of the target image and the first position information output by the image recognition model so as to acquire the target image recognition model.
4. The information acquisition method according to claim 1, wherein the authentication information processing position uploaded by the user terminal is determined by:
after receiving the information acquisition request sent by the user terminal, sending authentication information acquisition information to the user terminal, so that the user terminal acquires the authentication information according to the received authentication information acquisition information.
5. The method of claim 1, wherein the performing face verification on the received authentication information uploaded by the user terminal and performing location verification on the authentication information based on the target image recognition model includes:
extracting first face features of the environment image comprising the face image of the user;
Performing feature vector calculation on the first face feature and a second face feature when a user registers in the identity verification information to obtain a distance between the first face feature and the second face feature;
according to the distance, finishing face verification of the identity verification information;
and under the condition that the face verification is passed, carrying out position verification on the identity verification information based on the target image recognition model.
6. The information acquisition method according to claim 5, wherein the performing location verification of the authentication information based on the target image recognition model includes:
and inputting the environment image comprising the face image of the user into the target image recognition model, and completing the position verification of the identity verification information according to the comparison result of the fourth position information output by the target image recognition model and the position information of the user.
7. An information acquisition system, comprising: the system comprises a first training module, a second training module, an identity verification module and an information acquisition module;
the first training module is used for pre-training the convolutional neural network by using a first training sample so as to obtain an image recognition model;
The second training module is used for carrying out optimization training on the image recognition model by using a second training sample so as to obtain a target image recognition model;
the identity verification module is used for carrying out face verification on the received identity verification information uploaded by the user terminal and carrying out position verification on the identity verification information based on the target image recognition model;
the information acquisition module is used for transmitting the received data information corresponding to the information acquisition request transmitted by the user terminal to the user terminal under the condition that the face verification and the position verification are both passed;
the first training sample is obtained by marking each environment image according to first position information corresponding to each environment image in a plurality of acquired environment images;
the second training sample is determined according to a target image obtained by overlapping the face image and the environment image in the first training sample;
the identity verification information comprises an environment image including a face image of the user and position information of the user, wherein the environment image is shot by the user in real time.
8. An electronic device comprising a processor and a memory storing a computer program, characterized in that the processor implements the information acquisition method of any one of claims 1 to 6 when executing the computer program.
9. A processor-readable storage medium, characterized in that the processor-readable storage medium stores a computer program for causing the processor to execute the information acquisition method according to any one of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program, when executed by a processor, implements the information acquisition method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210272796.0A CN116824314A (en) | 2022-03-18 | 2022-03-18 | Information acquisition method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210272796.0A CN116824314A (en) | 2022-03-18 | 2022-03-18 | Information acquisition method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116824314A true CN116824314A (en) | 2023-09-29 |
Family
ID=88122672
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210272796.0A Pending CN116824314A (en) | 2022-03-18 | 2022-03-18 | Information acquisition method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116824314A (en) |
-
2022
- 2022-03-18 CN CN202210272796.0A patent/CN116824314A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020207189A1 (en) | Method and device for identity authentication, storage medium, and computer device | |
| TWI752418B (en) | Server, client, user authentication method and system | |
| US11276068B2 (en) | Fraudulent transaction identification method and apparatus, server, and storage medium | |
| CN106203242B (en) | Similar image identification method and equipment | |
| US11816880B2 (en) | Face recognition method and apparatus, computer device, and storage medium | |
| CN111680675B (en) | Face living body detection method, system, device, computer equipment and storage medium | |
| CN113591603B (en) | Certificate verification method and device, electronic equipment and storage medium | |
| US10963552B2 (en) | Method and electronic device for authenticating a user | |
| CN108108711B (en) | Face control method, electronic device and storage medium | |
| CN111553235B (en) | Network training method for protecting privacy, identity recognition method and device | |
| CN112650875A (en) | House image verification method and device, computer equipment and storage medium | |
| CN113642639B (en) | Living body detection method, living body detection device, living body detection equipment and storage medium | |
| CN113298158B (en) | Data detection method, device, equipment and storage medium | |
| CN108229375B (en) | Method and device for detecting face image | |
| CN112989308B (en) | Account authentication method, device, equipment and medium | |
| CN116524606A (en) | Face living body identification method and device, electronic equipment and storage medium | |
| TWM592131U (en) | Characteristic encoding system and internet bank service system applying the same | |
| CN116824314A (en) | Information acquisition method and system | |
| CN115082873A (en) | Image recognition method and device based on path fusion and storage medium | |
| CN115708135A (en) | Face recognition model processing method, face recognition method and device | |
| TWI774577B (en) | Identity identification system | |
| TWI696141B (en) | Feature coding system and method and online banking service system and method thereof using the same | |
| CN115775403A (en) | Living body identification method and device | |
| CN115862157A (en) | Living body attack detection method and training method of living body attack detection model | |
| CN117010899A (en) | Face payment method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |